Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/xobotyi/cc-foundry/bunnpx skills add xobotyi/cc-foundry --skill bungit clone --depth 1 https://github.com/xobotyi/cc-foundryWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/xobotyi/cc-foundry/bun)<a href="https://agentmods.dev/skills/xobotyi/cc-foundry/bun"><img src="https://agentmods.dev/badge/skills/xobotyi/cc-foundry/bun.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00055 | $0.06041 |
| Opus 5 | $0.00028 | $0.03021 |
| Sonnet 5 | $0.00011 | $0.01208 |
| Haiku 4.5 | $0.00006 | $0.00604 |
Grade B, and why
bun scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
When **reviewing** Bun, cite the violation and show the fix inline. Do not lecture. Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- **Shelling out** — `Bun.$` over `child_process.exec`, `zx`, `execa`, `cross-env`, and `rimraf` How it starts
The opening of the file, as written. The whole thing — 308 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bun's value is that the runtime, the toolchain, and the batteries are one binary. Two biases decide most calls:
- Reach for what already ships. A dependency earns its place by doing what
Bun.*,bun:*, and the bundled toolchain do not. Adding one that duplicates a built-in is a defect. - Write
node:only where Bun has no native equivalent, or where the code must also run under Node. Portability is a requirement to state, not a habit to keep.
Release Version
Bun ships one stable line and no long-lived support branches, so bun upgrade moves a machine to whatever release is
newest. Pin the version in CI (oven-sh/setup-bun, bun-version) so a developer machine and a runner agree, and state
the release a feature needs in the sentence that uses it. Never write "the latest version supports X".
The rules below assume 1.3.0 or later unless a version anchor says otherwise. Floors for the features these rules reference:
- 1.3.0 —
Bun.sqlfor MySQL, MariaDB, and SQLite;Bun.redis;Bun.secrets;Bun.YAML; catalogs;test.concurrent,test.serial, and--concurrent;--randomize;expectTypeOf - 1.3.2 — the isolated linker as the default for new monorepos;
nativeDependencies;ignoreScripts - 1.3.3 —
test(..., { retry }) - 1.3.4 —
jest.useFakeTimers();URLPattern;--compilestops auto-loadingtsconfig.jsonandpackage.json - 1.3.5 —
Bun.Terminal;Bun.stringWidth;bun:bundlefeature flags;trustedDependencieslimited to npm sources - 1.3.6 —
Bun.JSONC;Bun.Archive;Bun.build({ files });metafile: true - 1.3.7 —
Bun.JSON5;Bun.JSONL;Bun.wrapAnsi - 1.3.8 —
Bun.markdown;--metafile-md - 1.3.9 —
bun run --parallel; bytecode for ES modules - 1.3.10 —
optimizeImports; standard TC39 decorators;--compile --target=browserfor a single HTML file - 1.3.11 —
Bun.cron();Bun.sliceAnsi - 1.3.12 —
Bun.WebView - 1.3.13 —
bun test --parallel,--isolate,--shard,--changed;Rangeand conditional requests inBun.serve - 1.3.14 —
Bun.Image; the global virtual store; HTTP/3 inBun.serve; HTTP/2 and HTTP/3 infetch() - 1.4.0 — Node 26 compatibility;
Bun.XML;Bun.isStandaloneExecutable;Bun.spawn({ cgroup }); directory routes;bun audit fix,bun dedupe,bun prune,bun pm diff,bun pm licenses;bun test --timings;--asset;lockfileVersion: 2
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday Changed · +91 lines · +12 tokens per session bf9b67a1900f
- 5d ago First seen · 217 lines · 43 tokens per session scan B b2a1dca7095a
bun is a skill published in the GitHub repository xobotyi/cc-foundry (20 stars, last pushed 2d ago), licensed MIT. It adds 55 tokens to every session and 6,041 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 2 findings (strips warnings and disclaimers, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…